Browse State-of-the-Art › Unsupervised Anomaly Detection

Unsupervised Anomaly Detection

226 papers with code · 18 benchmarks · 27 datasets archive 2025-07-28

Computer VisionGraphsMiscellaneous

The objective of Unsupervised Anomaly Detection is to detect previously unseen rare objects or events without any prior knowledge about these. The only information available is that the percentage of anomalies in the dataset is small, usually less than 1%. Since anomalies are rare and unknown to the user at training time, anomaly detection in most cases boils down to the problem of modelling the normal data distribution and defining a measurement in this space in order to classify samples as anomalous or normal. In high-dimensional data such as images, distances in the original space quickly lose descriptive power (curse of dimensionality) and a mapping to some more suitable space is required.

Source: Unsupervised Learning of Anomaly Detection from Contaminated Image Data using Simultaneous Encoder Training

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

18 leaderboard tables shown for this task, 18 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 18 until expanded.

Syntology 10 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): SMAP (7 judged, 0 placed), MNIST (2 judged, 0 placed), SMD (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
AnoShift (15 rows) ACR-NTL (zero-shot, test anomaly ratio=1%) Zero-Shot Anomaly Detection via Batch Normalization code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
SMAP (9 rows) DFM (flow matching) DFM: Interpolant-free Dual Flow Matching — — Compare
Vehicle Claims (9 rows) SOM Unsupervised Anomaly Detection for Auditing Data and Impact of... code — Compare
KolektorSDD2 (3 rows) WeakREST-Un Industrial Anomaly Detection and Localization Using... — — Compare
20NEWS (1 row) RSRAE Robust Subspace Recovery Layer for Unsupervised Anomaly Detection code — Compare
AeBAD-S (1 row) MSFR Multi-scale feature reconstruction network for industrial anomaly detection code — Compare
Caltech-101 (1 row) RSRAE Robust Subspace Recovery Layer for Unsupervised Anomaly Detection code — Compare
DAGM2007 (1 row) DiffusionAD DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection code — Compare
ECG5000 (1 row) VRAE+SVM Learning Representations from Healthcare Time Series Data for... — — Compare
Fashion-MNIST (1 row) RSRAE Robust Subspace Recovery Layer for Unsupervised Anomaly Detection code — Compare
KolektorSDD (1 row) Semi-orthogonal Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation code — Compare
MNIST (1 row) LVAD Locally varying distance transform for unsupervised visual anomaly... code — Compare
PRONTO (1 row) DyEdgeGAT DyEdgeGAT: Dynamic Edge via Graph Attention for Early Fault... code — Compare
Reuters-21578 (1 row) RSRAE Robust Subspace Recovery Layer for Unsupervised Anomaly Detection code — Compare
SMD (1 row) TranAD TranAD: Deep Transformer Networks for Anomaly Detection in... code Syntology official: harvested, nothing ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified Compare
STL-10 (1 row) LVAD Locally varying distance transform for unsupervised visual anomaly... code — Compare
Synthetic (1 row) DyEdgeGAT DyEdgeGAT: Dynamic Edge via Graph Attention for Early Fault... code — Compare
TIMo (1 row) P-CAE W-MSE (Tilted View) Unsupervised Anomaly Detection from Time-of-Flight Depth Images — — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

27 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

5 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 506 · with a code link: 226 · where Syntology ran a sample: 58 (52 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (58 of 506 tagged: 52 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument)

Page 1 of 6: papers 1 to 100 of 506, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 41 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections